论文标题
一个柔软的最近的邻居框架，用于连续半监督学习
A soft nearest-neighbor framework for continual semi-supervised learning
论文作者
论文摘要
尽管取得了重大的进步，但最先进的持续学习方法的表现取决于完全标记的数据的不切实际情景。在本文中，我们解决了这一挑战，并提出了一种连续半监督学习的方法 - 并非所有数据样本都被标记。在这种情况下，主要问题是模型忘记了未标记的数据的表示形式并过度适合标记的样本。我们利用最近邻分分类器的功能将特征空间划分为非线性分区，并由于其非参数性质而灵活地对基础数据分布进行了建模。这使模型能够学习当前任务的强大表示，并从先前的任务中提取相关信息。我们进行了彻底的实验评估，并表明我们的方法的表现优于所有现有方法，从而在连续的半监督学习范式上设定了稳定的最新水平。例如，在CIFAR-100上，即使使用至少减少30倍的监督（0.8％比25％的注释），我们也超过了其他几个。最后，我们的方法在低分辨率图像和高分辨率图像和尺度上都可以很好地适用于更复杂的数据集，例如Imagenet-100。该代码在https://github.com/kangzhiq/nncsl上公开可用
Despite significant advances, the performance of state-of-the-art continual learning approaches hinges on the unrealistic scenario of fully labeled data. In this paper, we tackle this challenge and propose an approach for continual semi-supervised learning--a setting where not all the data samples are labeled. A primary issue in this scenario is the model forgetting representations of unlabeled data and overfitting the labeled samples. We leverage the power of nearest-neighbor classifiers to nonlinearly partition the feature space and flexibly model the underlying data distribution thanks to its non-parametric nature. This enables the model to learn a strong representation for the current task, and distill relevant information from previous tasks. We perform a thorough experimental evaluation and show that our method outperforms all the existing approaches by large margins, setting a solid state of the art on the continual semi-supervised learning paradigm. For example, on CIFAR-100 we surpass several others even when using at least 30 times less supervision (0.8% vs. 25% of annotations). Finally, our method works well on both low and high resolution images and scales seamlessly to more complex datasets such as ImageNet-100. The code is publicly available on https://github.com/kangzhiq/NNCSL
